Emergent Properties of Foveated Perceptual Systems

人工智能 计算机科学 人类视觉系统模型 计算机视觉 稳健性(进化) 卷积神经网络 视觉感受 感知 模式识别(心理学) 图像(数学) 生物化学 化学 神经科学 生物 基因
作者
Arturo Deza,Talia Konkle
摘要

We introduce foveated perceptual systems -- a hybrid architecture inspired by human vision, to explore the role of a \textit{texture-based} foveation stage on the nature and robustness of subsequently learned visual representation in machines. Specifically, these two-stage perceptual systems first foveate an image, inducing a texture-like encoding of peripheral information -- mimicking the effects of \textit{visual crowding} -- which is then relayed through a convolutional neural network (CNN) trained to perform scene categorization. We find that these foveated perceptual systems learn a visual representation that is \textit{distinct} from their non-foveated counterpart through experiments that probe: 1) i.i.d and o.o.d generalization; 2) robustness to occlusion; 3) a center image bias; and 4) high spatial frequency sensitivity. In addition, we examined the impact of this foveation transform with respect to two additional models derived with a rate-distortion optimization procedure to compute matched-resource systems: a lower resolution non-foveated system, and a foveated system with adaptive Gaussian blurring. The properties of greater i.i.d generalization, high spatial frequency sensitivity, and robustness to occlusion emerged exclusively in our foveated texture-based models, independent of network architecture and learning dynamics. Altogether, these results demonstrate that foveation -- via peripheral texture-based computations -- yields a distinct and robust representational format of scene information relative to standard machine vision approaches, and also provides symbiotic computational support that texture-based peripheral encoding has important representational consequences for processing in the human visual system.

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
yy发布了新的文献求助10
刚刚
wwm98656完成签到,获得积分10
3秒前
3秒前
totpto完成签到,获得积分20
4秒前
6秒前
My完成签到,获得积分10
6秒前
孙颖莎粉丝完成签到,获得积分10
6秒前
尼古拉耶维奇完成签到,获得积分10
6秒前
阿卡宁发布了新的文献求助10
7秒前
8秒前
温柔翰完成签到,获得积分10
9秒前
文龙完成签到 ,获得积分10
9秒前
10秒前
Xiaopan完成签到,获得积分10
10秒前
xiaoming发布了新的文献求助200
11秒前
11秒前
QT完成签到,获得积分20
12秒前
朱华彪完成签到,获得积分10
12秒前
活在当下发布了新的文献求助10
12秒前
12秒前
haha发布了新的文献求助10
13秒前
aurora完成签到 ,获得积分10
14秒前
茉莉完成签到,获得积分10
14秒前
123完成签到,获得积分10
16秒前
16秒前
wwewew完成签到,获得积分10
17秒前
saying发布了新的文献求助10
17秒前
123123完成签到,获得积分10
17秒前
隐形曼青应助阿卡宁采纳,获得10
18秒前
负责紊完成签到,获得积分10
18秒前
善良的火发布了新的文献求助10
20秒前
haha完成签到,获得积分10
20秒前
22秒前
sugar完成签到,获得积分10
23秒前
活在当下完成签到,获得积分10
23秒前
25秒前
ssy发布了新的文献求助10
25秒前
小嘉贞完成签到,获得积分10
27秒前
鸡蛋黄完成签到,获得积分10
28秒前
温纲完成签到,获得积分10
29秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
Research on Disturbance Rejection Control Algorithm for Aerial Operation Robots 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038524
求助须知:如何正确求助?哪些是违规求助? 3576221
关于积分的说明 11374737
捐赠科研通 3305912
什么是DOI,文献DOI怎么找? 1819354
邀请新用户注册赠送积分活动 892688
科研通“疑难数据库(出版商)”最低求助积分说明 815048